Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    instances of dialogue or quotes in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    warts
    -0.16
    gers
    -0.16
    cplusplus
    -0.15
    orca
    -0.15
    hem
    -0.15
    itura
    -0.14
    ea
    -0.14
    hap
    -0.14
    ikip
    -0.14
    enko
    -0.14
    POSITIVE LOGITS
     Moder
    0.16
    åĬ¿
    0.14
    _publisher
    0.14
    elay
    0.14
    Moder
    0.13
    abr
    0.13
     revolves
    0.13
    gfx
    0.13
     Gain
    0.13
     Luxury
    0.13
    Act Density 0.006%

    No Known Activations